In recent years, the accuracy of speech recognition has improved remarkably. Speech recognition software can be used to obtain text information from conversational speech data. Although text can be treated as surface level information, several studies have indicated that speech recognition can also be used to estimate emotions, which represent higher level information in a conversation. Several newly proposed models use LSTM or GRU to estimate emotion in conversations. However, when attempting to monitor or influence conversations conducted as part of a meeting or a chat, the mood of the conversation is more important than the emotion. In normal conversation, emotions such as anger and sadness are unlikely to be explicitly expressed for some purposes, including avoidance of getting into an unexpected argument and offending others. Thus, when attempting to control or monitor the state of a conversation during a meeting or casual discussion, it is often more important to estimate the mood than the emotion. Some researchers have examined the role of mood, as distinguished from emotion, and one called diffuse emotional states that persist over a long period of time "mood" and are usually distinguished based on duration and intensity of expression. However, these differences are rarely quantified, and no specific durations are fixed. Accurate identification of the mood of a conversation is especially important for Japanese people who are engaged in collaborative and democratic decision making. To construct the teacher data for the model designed to estimate the conversational mood, we first selected representative adjective pairs that could describe the conversational mood. We utilized a system developed by Iiba et al. to estimate 21 affective scales of adjective pairs from input text. The 21 adjective pairs were clustered into 4 groups based on the output scales. The 4 adjective pairs to be annotated were representative of the 4 clusters. We expected these 4 adjective pairs (gloomy-happy, easy-serious, calm-aggressive, tidy-messy) to capture the mood of a conversation.Based on the four adjective pairs, we constructed a new training data set containing 60 hours of conversations in Japanese. In this study, the data obtained only by microphones are used for estimation of conversational mood. The data set was annotated by the four adjective scales to learn the mood of the conversations. We de-veloped a LSTM deep neural network model that could read the "conversational mood" in real time. Furthermore, in our proposed neural network model, the amount of laughter which is generally measured by capturing facial expression with camera is also estimated together with the conversational mood. Because laughter is considered to play an important role in creating a cheerful environment, it can be used to evaluate the conversational mood. The evaluation results are shown to present the validity of our model. This model is expected to be applied to a system that can
{"title":"Neural Network Model for Visualization of Conversational Mood with Four Adjective Pairs","authors":"Koichi Yamagata, Koya Kawahara, Yuto Suzuki, Yuki Nakahodo, Shunsuke Ito, Haruka Matsukura, Maki Sakamoto","doi":"10.54941/ahfe1004396","DOIUrl":"https://doi.org/10.54941/ahfe1004396","url":null,"abstract":"In recent years, the accuracy of speech recognition has improved remarkably. Speech recognition software can be used to obtain text information from conversational speech data. Although text can be treated as surface level information, several studies have indicated that speech recognition can also be used to estimate emotions, which represent higher level information in a conversation. Several newly proposed models use LSTM or GRU to estimate emotion in conversations. However, when attempting to monitor or influence conversations conducted as part of a meeting or a chat, the mood of the conversation is more important than the emotion. In normal conversation, emotions such as anger and sadness are unlikely to be explicitly expressed for some purposes, including avoidance of getting into an unexpected argument and offending others. Thus, when attempting to control or monitor the state of a conversation during a meeting or casual discussion, it is often more important to estimate the mood than the emotion. Some researchers have examined the role of mood, as distinguished from emotion, and one called diffuse emotional states that persist over a long period of time \"mood\" and are usually distinguished based on duration and intensity of expression. However, these differences are rarely quantified, and no specific durations are fixed. Accurate identification of the mood of a conversation is especially important for Japanese people who are engaged in collaborative and democratic decision making. To construct the teacher data for the model designed to estimate the conversational mood, we first selected representative adjective pairs that could describe the conversational mood. We utilized a system developed by Iiba et al. to estimate 21 affective scales of adjective pairs from input text. The 21 adjective pairs were clustered into 4 groups based on the output scales. The 4 adjective pairs to be annotated were representative of the 4 clusters. We expected these 4 adjective pairs (gloomy-happy, easy-serious, calm-aggressive, tidy-messy) to capture the mood of a conversation.Based on the four adjective pairs, we constructed a new training data set containing 60 hours of conversations in Japanese. In this study, the data obtained only by microphones are used for estimation of conversational mood. The data set was annotated by the four adjective scales to learn the mood of the conversations. We de-veloped a LSTM deep neural network model that could read the \"conversational mood\" in real time. Furthermore, in our proposed neural network model, the amount of laughter which is generally measured by capturing facial expression with camera is also estimated together with the conversational mood. Because laughter is considered to play an important role in creating a cheerful environment, it can be used to evaluate the conversational mood. The evaluation results are shown to present the validity of our model. This model is expected to be applied to a system that can","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"128 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262493","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In eddy current testing, it is desirable to keep sensor perpendicular to test surface, but it is difficult to automatically determine the sensor posture at inspection points with complex geometry, and the non-destructive testing technician manually operates the sensor. In such cases, it is necessary to ensure skill of the technicians as they are part of the non-destructive testing system. We are conducting research to establish a skills training method to efficiently develop non-destructive testing technicians. The behavior of licensed and unlicensed subjects was measured while inspecting defects around bolt holes. There was a clear statistical difference between the sequences of licensed and unlicensed subjects.ts will be established, and a prototype real-time skill teaching system will be built to verify the validity of the proposed method.
{"title":"Quantitative Assessment of Eddy Current Inspection Technician Skills","authors":"Daigo Kosaka, Masahiro Hoshiba, Hiroyuki Nakamoto","doi":"10.54941/ahfe1004427","DOIUrl":"https://doi.org/10.54941/ahfe1004427","url":null,"abstract":"In eddy current testing, it is desirable to keep sensor perpendicular to test surface, but it is difficult to automatically determine the sensor posture at inspection points with complex geometry, and the non-destructive testing technician manually operates the sensor. In such cases, it is necessary to ensure skill of the technicians as they are part of the non-destructive testing system. We are conducting research to establish a skills training method to efficiently develop non-destructive testing technicians. The behavior of licensed and unlicensed subjects was measured while inspecting defects around bolt holes. There was a clear statistical difference between the sequences of licensed and unlicensed subjects.ts will be established, and a prototype real-time skill teaching system will be built to verify the validity of the proposed method.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Luis Filipe Rodrigues, Abilio Oliveira, Helena Rodrigues
In a time of digital disruption, users are deciding how they want banks to respond and even exceed their expectations. Banks rushed to face-lift their front-end look and enable non-essential digital services without acknowledging users’ needs. This recent attitude has harmed a good digital banking experience, and consequently the adoption of e-banking. To have a clear vision of how banks can stand out in a digital transformation 634 e-banking users were interviewed from the generations’ X, Y, and Z. A qualitative analysis was conducted using Leximancer software, to determine similarities and differences in three generations’ attitudes toward digital banking. The findings highlighted nineteen concepts grouped into eight key themes, namely: transfers, availability, use, speed, information, price, complex(ity), and market. Digital bank users are concerned about price, speed of transfers, and product information, valuing the easy availability of services and operations in the financial market, with some constraints about the complexity of options used to manage their accounts and savings. While Gen X (older age) looks at digital banking mainly for the availability of services, Gen Y (middle age) takes more advantage of digital banking to explore the bank/financial market and perform operations anywhere, and Gen Z (younger age) simply for transfers. This study contributes to understanding the adoption of digital banking, allowing to propose a new conceptual map to explain e-banking usage and identifying what is more important for each Gen X, Y, and Z generation may adopt digital banking.
{"title":"E-banking usage by Gen X, Y, and Z generations","authors":"Luis Filipe Rodrigues, Abilio Oliveira, Helena Rodrigues","doi":"10.54941/ahfe1004320","DOIUrl":"https://doi.org/10.54941/ahfe1004320","url":null,"abstract":"In a time of digital disruption, users are deciding how they want banks to respond and even exceed their expectations. Banks rushed to face-lift their front-end look and enable non-essential digital services without acknowledging users’ needs. This recent attitude has harmed a good digital banking experience, and consequently the adoption of e-banking. To have a clear vision of how banks can stand out in a digital transformation 634 e-banking users were interviewed from the generations’ X, Y, and Z. A qualitative analysis was conducted using Leximancer software, to determine similarities and differences in three generations’ attitudes toward digital banking. The findings highlighted nineteen concepts grouped into eight key themes, namely: transfers, availability, use, speed, information, price, complex(ity), and market. Digital bank users are concerned about price, speed of transfers, and product information, valuing the easy availability of services and operations in the financial market, with some constraints about the complexity of options used to manage their accounts and savings. While Gen X (older age) looks at digital banking mainly for the availability of services, Gen Y (middle age) takes more advantage of digital banking to explore the bank/financial market and perform operations anywhere, and Gen Z (younger age) simply for transfers. This study contributes to understanding the adoption of digital banking, allowing to propose a new conceptual map to explain e-banking usage and identifying what is more important for each Gen X, Y, and Z generation may adopt digital banking.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262893","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Hüseyin Şahan, Sultan Ceren Öner, Ahmet Tugrul Bayrak, İlker Baştürk, Olcay Taner Yıldız
There are billions of operations happening in a wide range of sectors on a daily basis. When it comes to the hospitality sector, it appears essential to handle POS operations in a more efficient way in restaurants. To fill the gap in the studies about event log data in the fast food restaurant POS context, an approach needs to be developed. Regarding these, in this study, restaurant event log data for taking orders are comprehensively analyzed using process mining principles and machine learning applications to increase productivity. After the discovery of processes, the bottlenecks of the existing system were extracted in fast food restaurant point of sale (POS). The main focus was determined as order-taking process times, which can be the most troubled part of the fast food delivery process. Regression analysis was conducted to identify possible reasons for increasing time for order taking in a restaurant pos. This analysis can extract the main drawbacks of the system and provide insights to solve problematic points in order to increase productivity. Process discovery techniques, such as heuristics miner, directly follows graph (DFG) are used under process mining methodologies to discover event logs in a visual manner in the background. To be able to understand the logic of event logs deeply, exploratory data analysis techniques were performed to identify the effect of log activity types by also focusing on their respective attributes. Afterwards, it needed to adopt performance analysis, comparative, and action-oriented process mining techniques to evaluate, identify, and operationally support the business. In addition to process mining approaches, feature engineering, descriptive statistics techniques and outlier elimination are used along with various regression methods such as XgBoost, Random Forest to identify the relationship between variables of the system. The detailed descriptions of the feature relations are also explained to understand how variables affect the order taking time directly or indirectly. After that, the study found possible reasons, such as how many products are sold or how many different operators are working on that POS, affecting ordering time and how much they are specific to its context. By identifying these reasons, it is shown that order-taking processing times in a restaurant POS can be dramatically decreased with specific recommended actions in particular contexts. By applying research findings, order-taking process times are expected to improve by around 21% in a territorial business, which implies productivity growth in POS environments. Consequently, the study first showed how different techniques can be used to identify outliers in relationship metrics in restaurant POS event log data. Secondly, it is a direct, crucial example of what factors affect a restaurant's POS processes and how much. Meanwhile, it significantly suggests machine learning integrated process mining approaches by combining the mentioned
{"title":"Evaluating Performance of Restaurant POS Processes in Fast-Food Restaurants","authors":"Hüseyin Şahan, Sultan Ceren Öner, Ahmet Tugrul Bayrak, İlker Baştürk, Olcay Taner Yıldız","doi":"10.54941/ahfe1004299","DOIUrl":"https://doi.org/10.54941/ahfe1004299","url":null,"abstract":"There are billions of operations happening in a wide range of sectors on a daily basis. When it comes to the hospitality sector, it appears essential to handle POS operations in a more efficient way in restaurants. To fill the gap in the studies about event log data in the fast food restaurant POS context, an approach needs to be developed. Regarding these, in this study, restaurant event log data for taking orders are comprehensively analyzed using process mining principles and machine learning applications to increase productivity. After the discovery of processes, the bottlenecks of the existing system were extracted in fast food restaurant point of sale (POS). The main focus was determined as order-taking process times, which can be the most troubled part of the fast food delivery process. Regression analysis was conducted to identify possible reasons for increasing time for order taking in a restaurant pos. This analysis can extract the main drawbacks of the system and provide insights to solve problematic points in order to increase productivity. Process discovery techniques, such as heuristics miner, directly follows graph (DFG) are used under process mining methodologies to discover event logs in a visual manner in the background. To be able to understand the logic of event logs deeply, exploratory data analysis techniques were performed to identify the effect of log activity types by also focusing on their respective attributes. Afterwards, it needed to adopt performance analysis, comparative, and action-oriented process mining techniques to evaluate, identify, and operationally support the business. In addition to process mining approaches, feature engineering, descriptive statistics techniques and outlier elimination are used along with various regression methods such as XgBoost, Random Forest to identify the relationship between variables of the system. The detailed descriptions of the feature relations are also explained to understand how variables affect the order taking time directly or indirectly. After that, the study found possible reasons, such as how many products are sold or how many different operators are working on that POS, affecting ordering time and how much they are specific to its context. By identifying these reasons, it is shown that order-taking processing times in a restaurant POS can be dramatically decreased with specific recommended actions in particular contexts. By applying research findings, order-taking process times are expected to improve by around 21% in a territorial business, which implies productivity growth in POS environments. Consequently, the study first showed how different techniques can be used to identify outliers in relationship metrics in restaurant POS event log data. Secondly, it is a direct, crucial example of what factors affect a restaurant's POS processes and how much. Meanwhile, it significantly suggests machine learning integrated process mining approaches by combining the mentioned ","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262902","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In response to urgent environmental sustainability and carbon reduction issues, the global transportation sector is actively promoting the use of electric vehicles to replace high-carbon emitting fuel vehicles. In the Taiwan two-wheeler market, for example, electric-scooter (e-scooter) products are increasingly meeting the needs of consumers due to their continuous lightweight and aesthetically designed improvements, as well as the provision of convenient battery swapping services. By the end of 2022, 2% of consumers in the overall scooter market had opted for e-scooters instead of fuel scooters, indicating that their needs were being satisfied. To further meet the consumer demand for e-scooters, Taiwan launched shared e-scooter services in 2018, enabling consumers to ride e-scooters by paying reasonable vehicle usage fees in a "rent-to-own" model to meet their transportation needs. As of the end of 2022, more than 8,000 e-scooters were made available for the public to share, satisfying the needs of consumers requiring short-distance transportation using e-scooters. From another perspective, the usage rate of private e-scooters is not high in Taiwan, with an average usage time of 54 minutes per private e-scooter. Since shared e-scooters are available for all users to consume, they can effectively reduce the idle rate of e-scooters and increase their usage rate, further meeting consumer needs. The primary goal of launching these products and services is to focus on sustainable transportation, as the simultaneous provision of these two service models can meet the needs of consumers with different transportation and usage habits, ultimately aiming to replace fuel vehicles.This research aims to gather subjective feedback from consumers through a rating scale to understand the extent to which e-scooters and shared e-scooters are meeting consumer needs, as well as the issues encountered during their usage, while prioritizing user experience and satisfaction by exploring the perceived feelings of users in their interaction with e-scooter products or shared e-scooter services. Participants with prior experience of using e-scooters or shared e-scooters will be recruited to complete the questionnaire. The final results of this study aim to provide recommendations for enhancing the services based on consumer feedback and gain insights into the demand for e-scooters and shared e-scooters, including analyzing the differences in demand for these products and proposing suggestions to better meet consumer needs. By addressing the challenges faced by consumers in using e-scooters and shared e-scooters, the results of this research will contribute to the development of more user-friendly and efficient transportation solutions, ultimately promoting the adoption of sustainable transportation options in Taiwan and globally, and supporting the reduction of carbon emissions while improving the quality of life for the public.
{"title":"Analyzing user experience of e-scooter usage: A human-computer interaction perspective on personal vs shared e-scooters","authors":"Huang Fei-Hui, Wen-chou Huang","doi":"10.54941/ahfe1004276","DOIUrl":"https://doi.org/10.54941/ahfe1004276","url":null,"abstract":"In response to urgent environmental sustainability and carbon reduction issues, the global transportation sector is actively promoting the use of electric vehicles to replace high-carbon emitting fuel vehicles. In the Taiwan two-wheeler market, for example, electric-scooter (e-scooter) products are increasingly meeting the needs of consumers due to their continuous lightweight and aesthetically designed improvements, as well as the provision of convenient battery swapping services. By the end of 2022, 2% of consumers in the overall scooter market had opted for e-scooters instead of fuel scooters, indicating that their needs were being satisfied. To further meet the consumer demand for e-scooters, Taiwan launched shared e-scooter services in 2018, enabling consumers to ride e-scooters by paying reasonable vehicle usage fees in a \"rent-to-own\" model to meet their transportation needs. As of the end of 2022, more than 8,000 e-scooters were made available for the public to share, satisfying the needs of consumers requiring short-distance transportation using e-scooters. From another perspective, the usage rate of private e-scooters is not high in Taiwan, with an average usage time of 54 minutes per private e-scooter. Since shared e-scooters are available for all users to consume, they can effectively reduce the idle rate of e-scooters and increase their usage rate, further meeting consumer needs. The primary goal of launching these products and services is to focus on sustainable transportation, as the simultaneous provision of these two service models can meet the needs of consumers with different transportation and usage habits, ultimately aiming to replace fuel vehicles.This research aims to gather subjective feedback from consumers through a rating scale to understand the extent to which e-scooters and shared e-scooters are meeting consumer needs, as well as the issues encountered during their usage, while prioritizing user experience and satisfaction by exploring the perceived feelings of users in their interaction with e-scooter products or shared e-scooter services. Participants with prior experience of using e-scooters or shared e-scooters will be recruited to complete the questionnaire. The final results of this study aim to provide recommendations for enhancing the services based on consumer feedback and gain insights into the demand for e-scooters and shared e-scooters, including analyzing the differences in demand for these products and proposing suggestions to better meet consumer needs. By addressing the challenges faced by consumers in using e-scooters and shared e-scooters, the results of this research will contribute to the development of more user-friendly and efficient transportation solutions, ultimately promoting the adoption of sustainable transportation options in Taiwan and globally, and supporting the reduction of carbon emissions while improving the quality of life for the public.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135262903","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rune Stensrud, Sigmund Valaker, Olav Rune Nummedal
Current uncrewed system (UxS) solutions tend to operate with tightly coupled Command and Control systems, making it difficult to contribute to operating as an integrated force. The case presented in this article is used to reason at the conceptual level about the different requirements and approaches for a future Norwegian UxS Integrated C2 system in order to inform the national development of an UxS Integrated C2 Reference Architecture. This is one in a series of papers that will develop a mission engineering approach and represents functional analysis needed for future acquisition of Norwegian UxS. Based on this work and the development of the situated Cognitive Engineering (sCE)-method eliciting knowledge, and knowledge acquisition information, we make key findings for outlining a strategic guide for an initial Norwegian UxS reference system and set-up (manning, organization and technical know-how).UxS solutions must be available to support ISR services for a variety of tasks and units on all military branches and levels. An UxS reference system must be adapted to the operational area and be available to operate within a harsh environment at the Northern Flank of NATO supporting those who need the information. Modern UxS solutions are based on human control and management, which entails human autonomy teaming which can be labour-intensive, with the potential for cognitive overload as well as bottlenecks in information processing. In the article, we presents a framework that support future acquisition of Norwegian UxS that suggests that autonomy must be distributed to reduce vulnerability and be scalable to handle emergency adapted the Northern Flank of NATO environment e.g. an autonomous system that interacts with its surroundings demonstrating a cooperative design approach with new opportunities (e.g. with and without AI support). We claim that a common future acquisition framework of Norwegian UxS applications (with AI) can reduce the burden on the operator based on results from our Functional Analysis (sCE-method) and empirical studies.
{"title":"Exploring Human autonomy teaming methods in challenging environments: the case of uncrewed system (UxS) solutions – challenges and opportunities (with AI)","authors":"Rune Stensrud, Sigmund Valaker, Olav Rune Nummedal","doi":"10.54941/ahfe1004307","DOIUrl":"https://doi.org/10.54941/ahfe1004307","url":null,"abstract":"Current uncrewed system (UxS) solutions tend to operate with tightly coupled Command and Control systems, making it difficult to contribute to operating as an integrated force. The case presented in this article is used to reason at the conceptual level about the different requirements and approaches for a future Norwegian UxS Integrated C2 system in order to inform the national development of an UxS Integrated C2 Reference Architecture. This is one in a series of papers that will develop a mission engineering approach and represents functional analysis needed for future acquisition of Norwegian UxS. Based on this work and the development of the situated Cognitive Engineering (sCE)-method eliciting knowledge, and knowledge acquisition information, we make key findings for outlining a strategic guide for an initial Norwegian UxS reference system and set-up (manning, organization and technical know-how).UxS solutions must be available to support ISR services for a variety of tasks and units on all military branches and levels. An UxS reference system must be adapted to the operational area and be available to operate within a harsh environment at the Northern Flank of NATO supporting those who need the information. Modern UxS solutions are based on human control and management, which entails human autonomy teaming which can be labour-intensive, with the potential for cognitive overload as well as bottlenecks in information processing. In the article, we presents a framework that support future acquisition of Norwegian UxS that suggests that autonomy must be distributed to reduce vulnerability and be scalable to handle emergency adapted the Northern Flank of NATO environment e.g. an autonomous system that interacts with its surroundings demonstrating a cooperative design approach with new opportunities (e.g. with and without AI support). We claim that a common future acquisition framework of Norwegian UxS applications (with AI) can reduce the burden on the operator based on results from our Functional Analysis (sCE-method) and empirical studies.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jessica Williams, Rhyse Bendell, Stephen Fiore, Florian Jentsch
Socially intelligent artificial agents have recently shown some evidence of improving team performance when advising human teammates during the execution of time-pressured, complex missions. These agents, imbued with a form of social intelligence supported by Artificial Theory of Mind, have also demonstrated some negative outcomes associated with their approaches to delivering advice and motivating teammates to succeed. Here, we closely examine team performance outcomes associated with a simulated team Urban Search and Rescue mission in the context of interventions delivered by artificial socially intelligent agents that served as advisors to the human teammates engaged in task execution. The task studied here required some individual taskwork effectiveness as well as a notable amount of interdependent teamwork coordination. The interdependent activities provided the advising artificially intelligent teammates an opportunity to observe and intervene to improve aspects of team process. Some of the interventions delivered by the socially intelligent agents were found to positively impact performance, notably those that targeted objective data and the dissemination of information to the right individual at appropriate timepoints; however, other interventions negatively impacted team outcomes. Results showed that Motivation interventions aimed solely at bolstering the motivation of team members did not yield positive outcomes; in fact, they were found to have adverse effects on overall team performance and task execution.
在执行时间紧迫、复杂的任务时，社会智能人工智能代理在为人类队友提供建议时，最近显示出一些改善团队绩效的证据。这些被人工心智理论(Artificial Theory of Mind)所支持的社会智能所渗透的代理人，在提供建议和激励队友取得成功的方法上也表现出了一些负面的结果。在这里，我们仔细研究了与模拟团队城市搜索和救援任务相关的团队绩效结果，在人工社会智能代理提供干预的背景下，人工社会智能代理作为参与任务执行的人类队友的顾问。这里研究的任务需要一些个人任务效率，以及大量的相互依赖的团队协调。相互依赖的活动为提供建议的人工智能团队成员提供了观察和干预的机会，以改进团队过程的各个方面。社会智能代理提供的一些干预措施被发现对绩效有积极影响，特别是那些针对客观数据和在适当的时间点向正确的个人传播信息的干预措施;然而，其他干预措施会对团队结果产生负面影响。结果表明，仅以增强团队成员的动机为目的的动机干预并没有产生积极的结果;事实上，他们被发现对整体团队绩效和任务执行有不利影响。
{"title":"Artificial Social Intelligence in Action: Lessons Learned from Human-Agent Hybrid Search and Rescue","authors":"Jessica Williams, Rhyse Bendell, Stephen Fiore, Florian Jentsch","doi":"10.54941/ahfe1004190","DOIUrl":"https://doi.org/10.54941/ahfe1004190","url":null,"abstract":"Socially intelligent artificial agents have recently shown some evidence of improving team performance when advising human teammates during the execution of time-pressured, complex missions. These agents, imbued with a form of social intelligence supported by Artificial Theory of Mind, have also demonstrated some negative outcomes associated with their approaches to delivering advice and motivating teammates to succeed. Here, we closely examine team performance outcomes associated with a simulated team Urban Search and Rescue mission in the context of interventions delivered by artificial socially intelligent agents that served as advisors to the human teammates engaged in task execution. The task studied here required some individual taskwork effectiveness as well as a notable amount of interdependent teamwork coordination. The interdependent activities provided the advising artificially intelligent teammates an opportunity to observe and intervene to improve aspects of team process. Some of the interventions delivered by the socially intelligent agents were found to positively impact performance, notably those that targeted objective data and the dissemination of information to the right individual at appropriate timepoints; however, other interventions negatively impacted team outcomes. Results showed that Motivation interventions aimed solely at bolstering the motivation of team members did not yield positive outcomes; in fact, they were found to have adverse effects on overall team performance and task execution.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As artificial intelligence (AI) seeks to improve modern society, the commercial aviation industry offers a significant opportunity. Although many parts of commercial aviation including maintenance, the ramp, and air traffic control show promise to integrate AI, the highly computerized digital flight deck (DFD) could be challenging. The researchers seek to understand what role AI could provide going forward by assessing AI evolution on the commercial flight deck over the past 50 years. A modified SHELL diagram is used to complete a Human Factors (HF) analysis of the early use for AI on the commercial flight deck through introduction of the Ground Proximity Warning System (GPWS), followed by the Enhanced GPWS (EGPWS) used currently, to demonstrate a form of Trustworthy AI (TAI). The recent Boeing 737 MAX 8 accidents are analyzed using an updated SHELL analysis that illustrates increased computer automation and information on the contemporary DFD. The 737 MAX 8 accidents and the role of the MCAS AI system are scrutinized to reveal the extent to which AI can fail and create distrust among end-users. Both analyses project what must be done to implement and integrate TAI effectively in a contemporary DFD design. The ergonomic evolution of AI on the commercial flight deck illustrates how it has helped achieve industry safety gains. Through gradual integration, the quest for pilot trust has been challenged when attempting to balance efficiency and safety in commercial flight. Preliminary data from a national survey of company pilots indicates that trust in AI is regarded positively in general, although less so when applied to personal involvement. Implications for DFD design incorporating more advanced AI are considered further within the realm of trust and reliability.
随着人工智能(AI)寻求改善现代社会，商用航空业提供了一个重要的机会。尽管商业航空的许多部分，包括维护、停机坪和空中交通管制，都有望整合人工智能，但高度计算机化的数字驾驶舱(DFD)可能具有挑战性。研究人员试图通过评估过去50年人工智能在商业飞行甲板上的演变，了解人工智能在未来可能发挥的作用。通过引入近地预警系统(GPWS)，使用修改的SHELL图来完成人工智能在商业飞行甲板上早期使用的人为因素(HF)分析，然后是目前使用的增进型GPWS (EGPWS)，以展示一种可信赖的人工智能(TAI)形式。最近的波音737 MAX 8事故分析使用了最新的SHELL分析，说明了计算机自动化程度的提高和当代DFD的信息。737 MAX 8事故和MCAS人工智能系统的作用被仔细审查，以揭示人工智能可能失败的程度，并在最终用户中造成不信任。两者都分析了在当代DFD设计中有效地实现和集成TAI必须做些什么。人工智能在商业飞行甲板上的人体工程学发展说明了它如何帮助实现行业安全收益。通过逐步整合，在试图平衡商业飞行的效率和安全时，对飞行员信任的追求受到了挑战。一项针对公司试点的全国性调查的初步数据表明，人们普遍认为对人工智能的信任是积极的，尽管在个人参与方面则不那么积极。将更先进的人工智能纳入DFD设计的影响在信任和可靠性领域得到进一步考虑。
{"title":"The Evolution of AI on the Commercial Flight Deck: Finding Balance between Efficiency and Safety While Maintaining the Integrity of Operator Trust","authors":"Mark Miller, Sam Holley, Leila Halawi","doi":"10.54941/ahfe1004175","DOIUrl":"https://doi.org/10.54941/ahfe1004175","url":null,"abstract":"As artificial intelligence (AI) seeks to improve modern society, the commercial aviation industry offers a significant opportunity. Although many parts of commercial aviation including maintenance, the ramp, and air traffic control show promise to integrate AI, the highly computerized digital flight deck (DFD) could be challenging. The researchers seek to understand what role AI could provide going forward by assessing AI evolution on the commercial flight deck over the past 50 years. A modified SHELL diagram is used to complete a Human Factors (HF) analysis of the early use for AI on the commercial flight deck through introduction of the Ground Proximity Warning System (GPWS), followed by the Enhanced GPWS (EGPWS) used currently, to demonstrate a form of Trustworthy AI (TAI). The recent Boeing 737 MAX 8 accidents are analyzed using an updated SHELL analysis that illustrates increased computer automation and information on the contemporary DFD. The 737 MAX 8 accidents and the role of the MCAS AI system are scrutinized to reveal the extent to which AI can fail and create distrust among end-users. Both analyses project what must be done to implement and integrate TAI effectively in a contemporary DFD design. The ergonomic evolution of AI on the commercial flight deck illustrates how it has helped achieve industry safety gains. Through gradual integration, the quest for pilot trust has been challenged when attempting to balance efficiency and safety in commercial flight. Preliminary data from a national survey of company pilots indicates that trust in AI is regarded positively in general, although less so when applied to personal involvement. Implications for DFD design incorporating more advanced AI are considered further within the realm of trust and reliability.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Core body temperature (CBT) is an important health indicator that denotes the temperature of the body core, and maintains brain and organ function. Invasive methods of CBT measurement pose challenges in assessing and monitoring human health. To address this, estimation of tympanic membrane temperature using multiple biological parameters often referenced for CBT has been attempted in previous studies. Our research focused on machine learning-based CBT estimation using hand-measurable biological data. Furthermore, while various studies have investigated machine learning models and the impact of information acquisition environments, few have compared the estimation accuracy of different biological parameters or assessed optimal feature combinations. Our proposed method entails the evaluation of indices in both normal scenarios with all variables and patterned scenarios with varying combinations of reduced explanatory variables. The comparison results reveal that when estimating the CBT based on skin conductance and pulse wave intervals excluding skin temperature, the mean absolute error, coefficient of determination, and root mean square error were 0.17 °C, 0.71, and 0.24 °C, respectively. This suggests that our approach is a feasible CBT estimation method that does not rely on skin temperature, although accuracy concerns persist. Furthermore, the estimation of the difference between CBT and skin temperature suggests that the estimation method may have accounted for individual variations within the data. Implementing the proposed method in increasingly popular smart rings and watches could facilitate the acquisition of CBT in daily life.
{"title":"Feature Selection for Machine Learning-Based Core Body Temperature Estimation Using Hand-Measurable Biological Information","authors":"Ryoya Oba, Keiichi Watanuki, Kazunori Kaede, Yusuke Osawa","doi":"10.54941/ahfe1004362","DOIUrl":"https://doi.org/10.54941/ahfe1004362","url":null,"abstract":"Core body temperature (CBT) is an important health indicator that denotes the temperature of the body core, and maintains brain and organ function. Invasive methods of CBT measurement pose challenges in assessing and monitoring human health. To address this, estimation of tympanic membrane temperature using multiple biological parameters often referenced for CBT has been attempted in previous studies. Our research focused on machine learning-based CBT estimation using hand-measurable biological data. Furthermore, while various studies have investigated machine learning models and the impact of information acquisition environments, few have compared the estimation accuracy of different biological parameters or assessed optimal feature combinations. Our proposed method entails the evaluation of indices in both normal scenarios with all variables and patterned scenarios with varying combinations of reduced explanatory variables. The comparison results reveal that when estimating the CBT based on skin conductance and pulse wave intervals excluding skin temperature, the mean absolute error, coefficient of determination, and root mean square error were 0.17 °C, 0.71, and 0.24 °C, respectively. This suggests that our approach is a feasible CBT estimation method that does not rely on skin temperature, although accuracy concerns persist. Furthermore, the estimation of the difference between CBT and skin temperature suggests that the estimation method may have accounted for individual variations within the data. Implementing the proposed method in increasingly popular smart rings and watches could facilitate the acquisition of CBT in daily life.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Barbara La Scaleia, Francesco Lacquaniti, Myrka Zago
Vestibular hypofunction due to aging or disease can be severely debilitating for daily life, causing dizziness, space disorientation, imbalance, limited mobility, and increased risk of falls. Current methods and techniques for vestibular rehabilitation often fail short of achieving stable, effective results due to the lack of physiologically-based, ergonomic approaches. Here we propose a novel approach based on the application of small-amplitude random displacements of the head and body, which can lead to enhanced vestibular function. The phenomenon we studied is akin to stochastic resonance, whereby the application of a given, optimal level of noise during periodic or non-periodic stimuli can determine an increased sensitivity in nonlinear systems, such as the vestibular perceptual system. The idea is that an appropriate level of noise can raise subthreshold stimuli above threshold, thereby making them detectable by the brain. We tested the protocol in a series of experiments involving 30 healthy young participants who were asked to discriminate the direction of whole-body motion imparted by a MOOG platform. Blindfolded subjects were presented with the discrimination of forward-backward single-cycle sinusoidal motion in a two-alternative forced-choice paradigm. The procedure followed an adaptive staircase. Vestibular threshold (i.e., minimum amplitude of applied motion that was discriminated by the subjects) was then computed from the slope of the psychometric function fitting the individual performance. We compared the vestibular threshold between the baseline condition (no external noise) and the conditions when band-limited white-noise was applied by the platform in the forward-backward direction. We found that in 26/30 participants the discrimination threshold was better with at least one noise level than that at baseline. The overall response curve roughly obeyed the bell-shaped function typical of stochastic resonance. We conclude that small-amplitude noise can ameliorate vestibular perception even in healthy young subjects. The advantage of this approach is that it is non-invasive and ecological, since it involves the application of small oscillations to the patient. Moreover, the task is easily understood since it consists of a classical discrimination paradigm.
{"title":"A novel stimulation protocol for vestibular rehabilitation","authors":"Barbara La Scaleia, Francesco Lacquaniti, Myrka Zago","doi":"10.54941/ahfe1004373","DOIUrl":"https://doi.org/10.54941/ahfe1004373","url":null,"abstract":"Vestibular hypofunction due to aging or disease can be severely debilitating for daily life, causing dizziness, space disorientation, imbalance, limited mobility, and increased risk of falls. Current methods and techniques for vestibular rehabilitation often fail short of achieving stable, effective results due to the lack of physiologically-based, ergonomic approaches. Here we propose a novel approach based on the application of small-amplitude random displacements of the head and body, which can lead to enhanced vestibular function. The phenomenon we studied is akin to stochastic resonance, whereby the application of a given, optimal level of noise during periodic or non-periodic stimuli can determine an increased sensitivity in nonlinear systems, such as the vestibular perceptual system. The idea is that an appropriate level of noise can raise subthreshold stimuli above threshold, thereby making them detectable by the brain. We tested the protocol in a series of experiments involving 30 healthy young participants who were asked to discriminate the direction of whole-body motion imparted by a MOOG platform. Blindfolded subjects were presented with the discrimination of forward-backward single-cycle sinusoidal motion in a two-alternative forced-choice paradigm. The procedure followed an adaptive staircase. Vestibular threshold (i.e., minimum amplitude of applied motion that was discriminated by the subjects) was then computed from the slope of the psychometric function fitting the individual performance. We compared the vestibular threshold between the baseline condition (no external noise) and the conditions when band-limited white-noise was applied by the platform in the forward-backward direction. We found that in 26/30 participants the discrimination threshold was better with at least one noise level than that at baseline. The overall response curve roughly obeyed the bell-shaped function typical of stochastic resonance. We conclude that small-amplitude noise can ameliorate vestibular perception even in healthy young subjects. The advantage of this approach is that it is non-invasive and ecological, since it involves the application of small oscillations to the patient. Moreover, the task is easily understood since it consists of a classical discrimination paradigm.","PeriodicalId":470195,"journal":{"name":"AHFE international","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135263412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：